In this paper, we investigate the diversity aspect of paraphrase generation. Prior deep learning models employ either decoding methods or add random input noise for varying outputs. We propose a simple method Diverse Paraphrase Generation (D-PAGE), which extends neural machine translation (NMT) models to support the generation of diverse paraphrases with implicit rewriting patterns. Our experimental results on two real-world benchmark datasets demonstrate that our model generates at least one order of magnitude more diverse outputs than the baselines in terms of a new evaluation metric Jeffrey's Divergence. We have also conducted extensive experiments to understand various properties of our model with a focus on diversity.
@article{arxiv.1808.04364,
title = {D-PAGE: Diverse Paraphrase Generation},
author = {Qiongkai Xu and Juyan Zhang and Lizhen Qu and Lexing Xie and Richard Nock},
journal= {arXiv preprint arXiv:1808.04364},
year = {2018}
}